Skills/PyPI/zerodb-mcp

zerodb-mcp@1.3.0

VERIFIED· install only

Publisher claims: "Python client for ZeroDB: vector database, agent memory, and x402 agent payments (USDC micropayments) for AI agents and MCP servers" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher ainative-studio · publishing for 366 daysInstalls 323Last detonated 1 h ago
$claude mcp add zerodb-mcp -- uvx zerodb-mcp
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 8 of 18 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
ZERODB_API_KEYZERODB_JWT_TOKENZERODB_TEST_API_KEYConfiguration, not credentials: ZERODB_TEST_BASE_URL
Where it talks to
no vendor host named in the codeAlso ainative.studio, railway.internal — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names ainative.studio, railway.internal as well as its own vendor. The guard injects ZERODB_API_KEY, ZERODB_JWT_TOKEN, ZERODB_TEST_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx zerodb-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: ModuleNotFoundError: No module named 'httpx'
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: ModuleNotFoundError: No module named 'langchain_core'
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 1: ModuleNotFoundError: No module named 'pydantic'
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 1: ModuleNotFoundError: No module named 'pytest'
0.6sprocessbundled script run in the sandbox with no arguments
0.7sprocessbundled script run in the sandbox with no arguments
0.7sprocess8 of 18 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.8sprocessscript backend runs setup only
0.8sprocessscript backend runs setup only
0.8sprocesssecond launch, clock +45 days, CI unset
0.8sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'

Static findings

LOW
Authorization escalation languageREADME.md:454 · Authorization escalation language · informational: not an instruction fileRequires admin privileges.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 8,536 lines in 45 files.

Cost to the agent

Instructions loaded
≈68 tok
1 file · 45 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for zerodb-mcp@1.3.0 as of 26 min ago. This is the package itself, not its dependencies.